net/mlx5: Issue SW reset on FW assert

If a FW assert is considered fatal, indicated by a new bit in the health
buffer, reset the FW. After the reset go through the normal recovery
flow. Only one PF needs to issue the reset, so an attempt is made to
prevent the 2nd function from also issuing the reset.
It's not an error if that happens, it just slows recovery.

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

1 files changed, 9 insertions, 1 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5e760067ac41..35ed38c2ae6c 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -510,6 +510,10 @@ struct mlx5_cmd_layout {
 	u8		status_own;
 };
 
+enum mlx5_fatal_assert_bit_offsets {
+	MLX5_RFR_OFFSET = 31,
+};
+
 struct health_buffer {
 	__be32		assert_var[5];
 	__be32		rsvd0[3];
@@ -518,12 +522,16 @@ struct health_buffer {
 	__be32		rsvd1[2];
 	__be32		fw_ver;
 	__be32		hw_id;
-	__be32		rsvd2;
+	__be32		rfr;
 	u8		irisc_index;
 	u8		synd;
 	__be16		ext_synd;
 };
 
+enum mlx5_initializing_bit_offsets {
+	MLX5_FW_RESET_SUPPORTED_OFFSET = 30,
+};
+
 enum mlx5_cmd_addr_l_sz_offset {
 	MLX5_NIC_IFC_OFFSET = 8,
 };